forztf avatar

Speckit Implement Zh

This is a Chinese language implementation workflow that takes you from approved specs to working code using a test-driven, sequential approach. It starts by checking prerequisite scripts, validates checklist completion (and blocks you if things aren't done unless you override), then loads your tasks.md, plan.md, and related spec files to execute implementation in phases: setup, tests, core, integration, polish. The interesting bit is how opinionated it gets about project hygiene, automatically creating or validating ignore files for git, Docker, ESLint, and whatever else it detects in your stack. It respects task dependencies, runs parallel tasks together when marked with [P], and stops on failures. Built for teams that want enforcement around spec-driven development rather than ad-hoc coding.

skills.sh installs
309
GitHub stars
10
last updated
Aug 21, 2026

Install

$ npx -y skills add forztf/open-skilled-sdd --skill speckit-implement-zh --agent claude-code

Installs into .claude/skills of the current project.

Files

用户输入

$ARGUMENTS

您必须在继续之前考虑用户输入(如果不为空)。

大纲

scripts: sh: .specify/scripts/bash/check-prerequisites.sh --json ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json

  1. 从仓库根目录运行 {SCRIPT} 并解析 FEATURE_DIR 和 AVAILABLE_DOCS 列表。所有路径必须是绝对的。对于参数中的单引号,如 "I'm Groot",使用转义语法:例如 'I'''m Groot'(或者如果可能的话使用双引号:"I'm Groot")。

  2. 检查检查表状态(如果 FEATURE_DIR/checklists/ 存在):

    • 扫描 checklists/ 目录中的所有检查表文件

    • 对于每个检查表,计数:

      • 总项目:所有匹配 - [ ] 或 - [X] 或 - [x] 的行
      • 完成项目:匹配 - [X] 或 - [x] 的行
      • 未完成项目:匹配 - [ ] 的行
    • 创建状态表:

      | 检查表 | 总计 | 已完成 | 未完成 | 状态 |
      |-----------|-------|-----------|------------|--------|
      | ux.md     | 12    | 12        | 0          | ✓ 通过 |
      | test.md   | 8     | 5         | 3          | ✗ 失败 |
      | security.md | 6   | 6         | 0          | ✓ 通过 |
      
    • 计算总体状态:

      • 通过:所有检查表都有 0 个未完成项目
      • 失败:一个或多个检查表有未完成项目
    • 如果有任何检查表未完成:

      • 显示包含未完成项目计数的表格
      • 停止并询问:"一些检查表未完成。您是否仍要继续执行实现?(yes/no)"
      • 等待用户响应后再继续
      • 如果用户说"no"或"wait"或"stop",则停止执行
      • 如果用户说"yes"或"proceed"或"continue",则继续到步骤 3
    • 如果所有检查表都完成:

Sponsors

Details

Repository
github.com/forztf/open-skilled-sdd
First seen
Jun 3, 2026

More from forztf/open-skilled-sdd

All 16

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs